Paper Citation Record · LEDGER

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary

As of 15 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2607.18553.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.18553 v3

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T15:08:39.272032Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3a85572e-bbce-4d02-b2d4-223c176b4fed · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Refusal in Language Models Is Mediated by a Single Direction

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:36.295096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8843568b-2476-4aef-a437-d13abbd3763e · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:36.361613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53abd113-7977-453a-8b82-67a813624b44 · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Tell me about yourself: LLMs are aware of their learned behaviors

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:36.489413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55c7487-df42-4a6c-9c8a-85b7ea894d76 · outbound

This paper cites Looking Inward: Language Models Can Learn About Themselves by Introspection.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Looking Inward: Language Models Can Learn About Themselves by Introspection

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:36.595363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04c97a1d-c13c-4ef4-84a8-2c6408658242 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Training Verifiers to Solve Math Word Problems

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:36.688961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e08785a-ba2b-413c-9aaf-c8314446764b · outbound

This paper cites Does It Make Sense to Speak of Introspection in Large Language Models?.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Does It Make Sense to Speak of Introspection in Large Language Models?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:36.808192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc735ae7-d981-4eb3-98cc-38534912a65d · outbound

This paper cites Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:36.957679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d19b981-b5a6-4ecb-a0bc-a1d8f74e08c7 · outbound

This paper cites Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.083536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f91fd41c-1765-4611-98b1-a9fa0227f239 · outbound

This paper cites Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.209421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb8a5515-6542-49c4-8898-5940e292126a · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Training Large Language Models to Reason in a Continuous Latent Space

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.294894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c21cdec-e57d-493b-98ea-bcfe95920b5d · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Measuring Mathematical Problem Solving With the MATH Dataset

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.337647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31021af6-423e-469e-9c57-fea260c51ae5 · outbound

This paper cites Relational Preference Encoding in Looped Transformer Internal States.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Relational Preference Encoding in Looped Transformer Internal States

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.483971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f733765-f9be-43b0-bd9c-a2579c0b9889 · outbound

This paper cites Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.570947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab92d01-2c5d-4eb5-a741-bcc0e7ffeb29 · outbound

This paper cites an unresolved cited work.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.638894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b279f1aa-f346-47f7-9a95-01b75c4c8360 · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.728924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee9dde9-c887-4ede-b44e-8cfc9300ca8b · outbound

This paper cites RewardBench: Evaluating Reward Models for Language Modeling.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary RewardBench: Evaluating Reward Models for Language Modeling

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.823880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e783a4-8731-4178-bc97-c6168f4e8e66 · outbound

This paper cites Wilson, Marcelo G.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Wilson, Marcelo G

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:37.963522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c0ca9a7-bccb-4f59-8e92-9f4a75f20660 · outbound

This paper cites Let's Verify Step by Step.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Let's Verify Step by Step

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.072198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d20524e9-2a3e-4faf-8a6a-1a8276f8adc3 · outbound

This paper cites an unresolved cited work.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.177717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 634aa0a5-c83d-4869-94d1-2fd3e3cc657f · outbound

This paper cites Mechanisms of Introspective Awareness.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Mechanisms of Introspective Awareness

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.349157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3965f418-3ed1-4778-818f-7b51dc2305eb · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.510698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d64d7624-f1d0-442a-a3f1-846587a8297c · outbound

This paper cites SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.619917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e0c29cb-0314-4fe4-91d2-51258a1fdd4f · outbound

This paper cites an unresolved cited work.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.660742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a6cfb9c-d00a-44b1-bc49-bbdd0057ead4 · outbound

This paper cites Reasoning with Latent Thoughts: On the Power of Looped Transformers.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Reasoning with Latent Thoughts: On the Power of Looped Transformers

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.761430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f963a0-f186-4bd9-a9c6-6f47bc7ad03d · outbound

This paper cites Privileged Self-Access Matters for Introspection in AI.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Privileged Self-Access Matters for Introspection in AI

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.855521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 563556a6-31d4-4c44-b5ab-e54fcd9796f8 · outbound

This paper cites Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:38.933972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8fca366-16c7-40da-9099-03a5f90da3c6 · outbound

This paper cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:39.020948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1f089ed-3f2d-4762-aee1-b3a92106f3e1 · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary SGLang: Efficient Execution of Structured Language Model Programs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:39.087639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6bcd5c5-6398-40be-937b-55dca6a6b0d8 · outbound

This paper cites Scaling Latent Reasoning via Looped Language Models.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Scaling Latent Reasoning via Looped Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:39.191224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df708262-05cd-4e72-9a3e-c30f88663e00 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary Representation Engineering: A Top-Down Approach to AI Transparency

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T15:08:39.272032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.